4 papers
The promising potential of vision language models for the generation of textual weather forecasts
Edward C. C. Steele, Dinesh Mane, Emilio Monti +14
Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspirat…
Handling Ontology Gaps in Semantic Parsing
Andrea Bacciu, Marco Damonte, Marco Basaldella +1
The majority of Neural Semantic Parsing (NSP) models are developed with the assumption that there are no concepts outside the ones such models can represent with their target symbo…
MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection
Michael Regan, Shira Wein, George Baker +1
Abstract Meaning Representation (AMR) is a semantic formalism that captures the core meaning of an utterance. There has been substantial work developing AMR corpora in English and…
Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding
Zheng Zhao, Emilio Monti, Jens Lehmann +1
Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially re…